et-backend: Q8_0 matrix-engine GEMM kernel for prefill#25
Merged
marty1885 merged 1 commit intoJul 24, 2026
Merged
Conversation
RehanQasim-dev
marked this pull request as draft
July 23, 2026 11:13
github-actions
Bot
added
documentation
RehanQasim-dev
force-pushed
the
upstream-q8_0-tensor-gemm
branch
from
July 23, 2026 11:16
d776a72 to
7674a23
Compare
Adds a Q8_0 matrix-engine mul_mat kernel with static-reuse dequant across N-tiles and K-splitting, plus fused bias support for MUL_MAT+ADD. Routes N >= 47 to the matrix engine and N <= 47 to vecdot. Registers the new kernel in the KERNELS list, which it was missing from, so the runtime kernel lookup was silently failing and leaving the destination buffer unwritten. Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai>
RehanQasim-dev
force-pushed
the
upstream-q8_0-tensor-gemm
branch
from
July 23, 2026 11:21
7674a23 to
8bc517d
Compare
RehanQasim-dev
removed
documentation
RehanQasim-dev
marked this pull request as ready for review
July 23, 2026 11:59
|
Tested and I can replicate the performance. Decode is still coherent. Looks good! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Adds a Q8_0 matrix-engine mul_mat kernel with static-reuse dequant across N-tiles and K-splitting, plus fused bias support for MUL_MAT+ADD. Routes N >= 47 to the matrix engine and N <= 47 to vecdot.
Prefill improves roughly 6-9x on Llama-3.2-1B. Decode is unchanged since decode (N=1) always routes to the vecdot kernel, not the matrix-engine path this PR touches.
Additional information
Performance (Llama-3.2-1B-Instruct, ET-SoC-1):
Prefill t/s
Verified with llama-cli on ET-SoC-1 hardware (Llama-3.2-1B-Instruct).
Requirements